Pozicioniranje objekata u zatvorenim prostorima korištenjem označivača pozicije u prisustvu smetnji

undergraduate thesis

• Title (english): Indoor Positioning with Beacons in High-Interference Environments
• Author: Eduardo Marić
• Mentor: Marin Vuković (mentor)
• Committee member: Marin Vuković (predsjednik povjerenstva)
• Committee member: Ivan Slivar (član povjerenstva)
• Committee member: Renato Šoić (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2018-07-13, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Mogućnost preciznog lociranja objekata u unutarnjem prostoru daje mnoštvo korisnih primjena, od praćenja objekata u skladištima do navigacije osoba kroz zatvorene prostore. No, problem predstavljaju prostori u kojima se mogu pojaviti smetnje u propagaciji signala, kao što su industrijski pogoni. Postoji niz tehnologija koje se koriste pri lociranju u zatvorenim prostorima od čega je Bluetooth Low Energy najčešće korištena. Pri lociranju koristeći jačinu signala potrebno je voditi računa o pretvorbi vrijednosti u udaljenost u metrima, s obzirom na to da su vrijednosti jačine signala promjenjive te osjetljive na svoju okolinu. Toplinske mape stvorene na temelju takvih statičkih očitanja nisu pogodne za određivanje lokacije u prisustvu smetnji zbog promjena u fizičkom prostoru pomicanjem i dodavanjem metalnih objekata. Predloženo rješenje tome problemu je stvaranje više toplinskih mapa s različitim rasporedom prepreka signalu (metalnih objekata), te stvaranje i treniranje neuronske mreže, koja će na temelju danih jačina signala procijeniti lokaciju uređaja.

Abstract (english)

The ability to locate an object indoors has many possible applications, ranging from locating objects within wearhouses to navigating visitors inside buildings. The problem arises in areas with high interferences like industrial factories. There are many technologies used for indoor locationing, out of which Bluetooth Low Energy is the most commonly used. While locating, its important to account for variations in values of radio signal strength and its conversion into meters, since radio signal strength values are sensitive to their sourroundings. Heatmaps created based on such static readings will yield incorrect results in spaces with interferences, because of the change in position and number of metal objects through time. The suggested solution to this problem is creating multiple heatmaps, made with values read in different interference spaces (layouts of metal objects), on which a neural network will be trained. Using given radio signal strength informations the neural network should yield precise location coordinates.

• Keywords: pozicioniranje; zatvoreni prostori; trilateracija; BLE; UWB; neuronske mreže; interferencija; toplinske mape
• Keywords (english): positioning; indoor spaces; trilateration; Bluetooth; Ultra Wideband; neural networks; interference; heatmaps; beacons
• Language: croatian
• URN:NBN: urn:nbn:hr:168:991734
• Study programme: Title: Computing; Study programme type: university; Study level: undergraduate; Academic / professional title: sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva (sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2019-03-13 22:38:31